View Full Document

Improving Generalization with Active Learning



View the full content.
View Full Document
View Full Document

1 views

Unformatted text preview:

Machine Learning 15 201 221 1994 1994 Kluwer Academic Publishers Boston Manufactured in The Netherlands Improving Generalization with Active Learning DAVID COHN COHN PSYCHE MIT EDU Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA 02139 LES ATLAS Deptartment of Electrical Engineering University of Washington Seattle WA 98195 RICHARD LADNER Deptartment of Computer Science and Engineering University of Washington Seattle WA 98195 Editor Alex Waibel Abstract Active learning differs from learning from examples in that the learning algorithm assumes at least some control over what part of the input domain it receives information about In some situations active learning is provably more powerful than learning from examples alone giving better generalization for a fixed number of training examples In this article we consider the problem of learning a binary concept in the absence of noise We describe a formalism for active concept learning called selective sampling and show how it may be approximately implemented by a neural network In selective sampling a learner receives distribution information from the environment and queries an oracle on parts of the domain it considers useful We test our implementation called an SGnetwork on three domains and observe significant improvement in generalization Keywords queries active learning generalization version space neural networks 1 Introduction Random sampling vs active learning Most neural network generalization problems are studied only with respect to random sampling the training examples are chosen at random and the network is simply a passive learner This approach is generally referred to as learning from examples Baum and Haussler 1989 examine the problem analytically for neural networks Conn and Tesauro 1992 provide an empirical study of neural network generalization when learning from examples There have also been a number of empirical efforts such as those of Le Cun et al 1990



Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Improving Generalization with Active Learning and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Improving Generalization with Active Learning and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?